FireRed-Image-Edit-1.0 Technical Report
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912915904266240 |
|---|---|
| author | Super Intelligence Team Qiao, Changhao Hui, Chao Li, Chen Wang, Cunzheng Song, Dejia Zhang, Jiale Li, Jing Xiang, Qiang Wang, Runqi Sun, Shuang Zhu, Wei Tang, Xu Hu, Yao Chen, Yibo Huang, Yuhao Duan, Yuxuan Chen, Zhiyi Guo, Ziyuan |
| author_facet | Super Intelligence Team Qiao, Changhao Hui, Chao Li, Chen Wang, Cunzheng Song, Dejia Zhang, Jiale Li, Jing Xiang, Qiang Wang, Runqi Sun, Shuang Zhu, Wei Tang, Xu Hu, Yao Chen, Yibo Huang, Yuhao Duan, Yuxuan Chen, Zhiyi Guo, Ziyuan |
| contents | We present FireRed-Image-Edit, a diffusion transformer for instruction-based image editing that achieves state-of-the-art performance through systematic optimization of data curation, training methodology, and evaluation design. We construct a 1.6B-sample training corpus, comprising 900M text-to-image and 700M image editing pairs from diverse sources. After rigorous cleaning, stratification, auto-labeling, and two-stage filtering, we retain over 100M high-quality samples balanced between generation and editing, ensuring strong semantic coverage and instruction alignment. Our multi-stage training pipeline progressively builds editing capability via pre-training, supervised fine-tuning, and reinforcement learning. To improve data efficiency, we introduce a Multi-Condition Aware Bucket Sampler for variable-resolution batching and Stochastic Instruction Alignment with dynamic prompt re-indexing. To stabilize optimization and enhance controllability, we propose Asymmetric Gradient Optimization for DPO, DiffusionNFT with layout-aware OCR rewards for text editing, and a differentiable Consistency Loss for identity preservation. We further establish REDEdit-Bench, a comprehensive benchmark spanning 15 editing categories, including newly introduced beautification and low-level enhancement tasks. Extensive experiments on REDEdit-Bench and public benchmarks (ImgEdit and GEdit) demonstrate competitive or superior performance against both open-source and proprietary systems. We release code, models, and the benchmark suite to support future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13344 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FireRed-Image-Edit-1.0 Technical Report Super Intelligence Team Qiao, Changhao Hui, Chao Li, Chen Wang, Cunzheng Song, Dejia Zhang, Jiale Li, Jing Xiang, Qiang Wang, Runqi Sun, Shuang Zhu, Wei Tang, Xu Hu, Yao Chen, Yibo Huang, Yuhao Duan, Yuxuan Chen, Zhiyi Guo, Ziyuan Computer Vision and Pattern Recognition Image and Video Processing We present FireRed-Image-Edit, a diffusion transformer for instruction-based image editing that achieves state-of-the-art performance through systematic optimization of data curation, training methodology, and evaluation design. We construct a 1.6B-sample training corpus, comprising 900M text-to-image and 700M image editing pairs from diverse sources. After rigorous cleaning, stratification, auto-labeling, and two-stage filtering, we retain over 100M high-quality samples balanced between generation and editing, ensuring strong semantic coverage and instruction alignment. Our multi-stage training pipeline progressively builds editing capability via pre-training, supervised fine-tuning, and reinforcement learning. To improve data efficiency, we introduce a Multi-Condition Aware Bucket Sampler for variable-resolution batching and Stochastic Instruction Alignment with dynamic prompt re-indexing. To stabilize optimization and enhance controllability, we propose Asymmetric Gradient Optimization for DPO, DiffusionNFT with layout-aware OCR rewards for text editing, and a differentiable Consistency Loss for identity preservation. We further establish REDEdit-Bench, a comprehensive benchmark spanning 15 editing categories, including newly introduced beautification and low-level enhancement tasks. Extensive experiments on REDEdit-Bench and public benchmarks (ImgEdit and GEdit) demonstrate competitive or superior performance against both open-source and proprietary systems. We release code, models, and the benchmark suite to support future research. |
| title | FireRed-Image-Edit-1.0 Technical Report |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2602.13344 |